FASSILA: A Corpus for Algerian Dialect Fake News Detection and Sentiment Analysis

Abstract

In the context of low-resource languages, the Algerian dialect (AD) faces challenges due to the absence of annotated corpora, hindering its effective processing, notably in Machine Learning (ML) applications reliant on corpora for training and assessment. This study outlines the development process of a specialized corpus for Fake News (FN) detection and sentiment analysis (SA) in AD called FASSILA. This corpus comprises 10,087 sentences, encompassing over 19,497 unique words in AD, addresses the language's significant lack of linguistic resources, and covers seven distinct domains. We propose an FN detection and SA annotation scheme detailing the data collection, cleaning, and labeling. The remarkable Inter-Annotator Agreement indicates that the annotation scheme produces high-quality and consistent annotations. Subsequent classification experiments using BERT-based and ML models are presented, demonstrating promising results and highlighting avenues for further research. The dataset is currently freely available to facilitate future advancements in the field.